© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116900
    Prev
    Next
    INDEX
    Explanations

    Q:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fön
    -0.84
     espada
    -0.82
     constate
    -0.82
    င
    -0.79
     begins
    -0.78
     完了
    -0.78
    겁
    -0.78
    Groetjes
    -0.75
     তারিখ
    -0.75
     during
    -0.74
    POSITIVE LOGITS
     necesarios
    0.91
    SS
    0.86
    need
    0.85
    rowser
    0.83
     necesidad
    0.83
    urgeon
    0.82
    ต้อง
    0.82
    前半
    0.80
    onej
    0.79
    SP
    0.79
    Activations Density 0.001%

    No Known Activations